{"id":"https://openalex.org/W4405633181","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800148","title":"A Preliminary Study On End-to-End Multimodal Subtitle Recognition for Taiwanese TV Programs","display_name":"A Preliminary Study On End-to-End Multimodal Subtitle Recognition for Taiwanese TV Programs","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633181","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800148"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108913417","display_name":"Pei-Chung Su","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Pei-Chung Su","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021183142","display_name":"Cheng-Hsiu Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Hsiu Cho","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111415477","display_name":"Chih-Chung Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Chung Kuo","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045461759","display_name":"Yen\u2010Chun Lai","orcid":"https://orcid.org/0000-0002-4703-5708"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yen-Chun Lai","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101992437","display_name":"Yanming Lin","orcid":"https://orcid.org/0000-0001-9056-7972"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yan-Ming Lin","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050297067","display_name":"Chao-Shih Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chao-Shih Huang","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082271172","display_name":"Yuan\u2010Fu Liao","orcid":"https://orcid.org/0000-0003-0191-2178"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Fu Liao","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5108913417"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41399861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10759","display_name":"Translation Studies and Practices","score":0.9835000038146973,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/subtitle","display_name":"Subtitle","score":0.877979040145874},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6426769495010376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6418024301528931},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4239838719367981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35291579365730286},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08615469932556152}],"concepts":[{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.877979040145874},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6426769495010376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6418024301528931},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4239838719367981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35291579365730286},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08615469932556152}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3138516171","https://openalex.org/W4312233877","https://openalex.org/W4382202677","https://openalex.org/W4402727764","https://openalex.org/W6769311223","https://openalex.org/W6784333009","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1950334511","https://openalex.org/W3119551990","https://openalex.org/W2351264416","https://openalex.org/W3004133161","https://openalex.org/W2370494932","https://openalex.org/W2975517425","https://openalex.org/W4404782863"],"abstract_inverted_index":{"Taigi":[0],"or":[1],"Taiwanese,":[2],"once":[3],"widely":[4],"spoken":[5],"throughout":[6],"Taiwan,":[7],"has":[8],"experienced":[9],"a":[10,105],"significant":[11],"decline":[12],"and":[13,51,81,94,138],"is":[14,146,154],"now":[15],"considered":[16],"endangered.":[17],"This":[18,41],"research":[19],"aims":[20],"to":[21,34,74,98],"develop":[22],"an":[23,62],"end-to-end":[24],"subtitles":[25,76,108,122,135,145,153],"recognition":[26,123],"model":[27,124],"that":[28],"can":[29],"annotate":[30],"Taiwanese":[31,38,56,69,144],"TV":[32,117],"programs":[33,118],"automatically":[35],"create":[36],"large-scale":[37],"au-diovisual":[39],"datasets.":[40],"effort":[42],"supports":[43],"the":[44,52,55,126,141,149],"development":[45],"of":[46,54,131],"advanced":[47],"multi-modal":[48],"AI":[49],"models":[50,73],"preservation":[53],"language.":[57],"Our":[58,121],"approach":[59],"involves":[60],"developing":[61],"\u201cEnd-to-End":[63],"Multimodal":[64],"Subtitles":[65],"Recognition\u201c":[66],"system":[67],"for":[68,133,143,151],"TV,":[70],"which":[71],"requires":[72],"generate":[75],"by":[77],"integrating":[78],"simultaneous":[79],"textual":[80],"visual":[82],"information.":[83],"Further-more,":[84],"several":[85],"large":[86],"language":[87],"model-based":[88],"decoders,":[89],"such":[90],"as":[91],"BART,":[92],"GPT-2,":[93],"LLaMA2,":[95],"were":[96],"fine-tuned":[97],"improve":[99],"performance.":[100],"To":[101],"validate":[102],"our":[103],"approach,":[104],"multimodal":[106],"audi-ovisual":[107],"dataset":[109],"comprising":[110],"238,713":[111],"video":[112],"segments":[113],"from":[114],"PTS-Taigi":[115],"[1]":[116],"was":[119],"created.":[120],"achieved":[125],"CER":[127,142,150],"(Character":[128],"Error":[129],"Rate)":[130],"9.37%":[132],"bilingual":[134],"in":[136],"Chinese":[137,152],"Taiwanese.":[139],"Specifically,":[140],"4.43%,":[147],"while":[148],"16.54%.":[155]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
